Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5101 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1415056 (Python Code)

Max Activating Token Index: 214

Text #1

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4481. Min Act: -0.0000

Data Index: 609809 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1458206 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4716. Min Act: -0.0000

Data Index: 500030 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1382721 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1634898 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1417653 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4049. Min Act: -0.0000

Data Index: 581516 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4220. Min Act: -0.0000

Data Index: 239741 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3744. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1619594 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1540351 (Python Code)

Max Activating Token Index: 746

Text #12

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1364421 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1604385 (Python Code)

Max Activating Token Index: 221

Text #14

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1639289 (Python Code)

Max Activating Token Index: 847

Text #15

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1530183 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1539642 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3723. Min Act: -0.0000

Data Index: 963048 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1292533 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1196464 (C4 (Web Text))

Max Activating Token Index: 640